Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2007 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1081523 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3959. Min Act: 0.0000

Data Index: 1357450 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3911. Min Act: 0.0000

Data Index: 325799 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3735. Min Act: -0.0000

Data Index: 518187 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3655. Min Act: -0.0000

Data Index: 422165 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3623. Min Act: 0.0000

Data Index: 429693 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3824. Min Act: -0.0000

Data Index: 930574 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3641. Min Act: -0.0000

Data Index: 991106 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3510. Min Act: -0.0000

Data Index: 496572 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1085926 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1079145 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3554. Min Act: -0.0000

Data Index: 596389 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3368. Min Act: -0.0000

Data Index: 286945 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3280. Min Act: -0.0000

Data Index: 828548 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3571. Min Act: -0.0000

Data Index: 66817 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3281. Min Act: -0.0000

Data Index: 231398 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3265. Min Act: 0.0000

Data Index: 330564 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3219. Min Act: -0.0000

Data Index: 511409 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1126726 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3433. Min Act: 0.0001

Data Index: 605066 (C4 (Web Text))

Max Activating Token Index: 225